CN117707442B - Printer consumable management method and device - Google Patents
Printer consumable management method and device Download PDFInfo
- Publication number
- CN117707442B CN117707442B CN202410141771.6A CN202410141771A CN117707442B CN 117707442 B CN117707442 B CN 117707442B CN 202410141771 A CN202410141771 A CN 202410141771A CN 117707442 B CN117707442 B CN 117707442B
- Authority
- CN
- China
- Prior art keywords
- consumable
- data
- time
- point
- prediction result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title description 12
- 238000000034 method Methods 0.000 claims abstract description 47
- 239000000463 material Substances 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 13
- 238000009499 grossing Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000001932 seasonal effect Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000007639 printing Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000007637 random forest analysis Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for managing consumable materials of a printer, and relates to the technical field of intelligent control, wherein the method comprises the following steps: dynamically adjusting the influence factors according to the first prediction result and the historical data to obtain dynamic influence factors; predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors to obtain a second prediction result; calculating a final consumable replacement time point according to the second prediction result and the historical data; and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point. The method can accurately predict the residual consumption of the consumable and the predicted depletion time, can maximize the use efficiency of the consumable and reduce waste.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a method and a device for managing consumable materials of a printer.
Background
Printers play an important role in daily office, commercial printing, and personal use. The management of consumables, particularly cartridges or toner cartridges, is critical to ensure efficient operation of the printer. An untimely replacement of the consumable material may lead to a degradation of the print quality or an interruption of the printing, whereas a premature replacement may result in a waste of resources.
Limitations of the existing consumable management methods:
traditional consumable management methods may predict consumable life based only on simple algorithms, such as estimating the number of printed pages or time of use. These methods may be inaccurate and may not be adaptable to a variety of factors such as printing habits of different users, types of printed content, and specific models of printers.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a device for managing consumable materials of a printer, which can accurately predict the residual consumption of the consumable materials and the predicted depletion time, can maximize the use efficiency of the consumable materials and reduce waste.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a method of printer consumable management, comprising:
according to a preset consumable prediction model and the real-time state of consumable, primarily predicting the residual consumption and predicted depletion time of the consumable to obtain a first prediction result;
dynamically adjusting the influence factors according to the first prediction result and the historical data to obtain dynamic influence factors;
predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors to obtain a second prediction result;
calculating a final consumable replacement time point according to the second prediction result and the historical data;
and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
Further, according to a preset consumable prediction model and a real-time state of consumable, preliminary prediction is performed on the residual usage amount and the predicted depletion time of the consumable to obtain a first prediction result, including:
acquiring real-time data related to the consumable and historical use data of the consumable;
extracting key features according to real-time data related to the consumable and historical use data of the consumable;
determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point;
mapping each data point to a corresponding position on the circumference according to the angle value corresponding to each data point;
calculating the distance between each data point and the circle center according to the corresponding position of each data point on the circle;
screening each data point according to the distance between each data point and the circle center to obtain screening data;
preprocessing the screening data to obtain preprocessed data;
and predicting the residual consumption and the predicted depletion time of the consumable according to the preprocessing data and a preset consumable prediction model to obtain a first prediction result.
Further, dynamically adjusting the influence factor according to the first prediction result and the history data to obtain a dynamic influence factor, including:
acquiring a first prediction resultData set +.>Wherein, the method comprises the steps of, wherein,，/>is a consumable predictive model parameter set,/->Representing historical dataset +.>The%>Individual observations->And->Corresponding consumable predictive model parameters;
by passing throughCalculating dynamic influence factor->Wherein->={/>，/>，…，/>… is the parameter set of the influence factor adjustment model, +.>And->Is the influence factor to adjust the model parameters,/->Is thatsigmoidAnd a function for smoothing and adjusting the influence of the prediction result and the history data.
Further, predicting the remaining consumption of the consumable and the predicted depletion time according to the dynamic influence factor to obtain a second predicted result, including:
is provided withARMA(p，q) The order of the autoregressive terms is represented aspThe order of the moving average term isqThe time series model of consumable consumption data is:wherein->And->Is a time series model parameter, < >>Is an error term->Is a trend component->Is a seasonal component;
by passing throughPredicting the remaining consumption of the consumable and the predicted depletion time to obtain a second prediction result +.>Wherein->Is historical consumption data, < >>Is a dynamic influencing factor, ++>Is a machine learning model for predicting the remaining amount of consumable,wherein->，/>，And->Parameters (I)>Is a function ofThe estimated depletion time is calculated.
Further, calculating a final consumable replacement time point according to the second prediction result and the historical data, including:
by passing throughCalculate the final replacement consumable time point +.>，/>Indicates the current time, ++>Indicating the remaining consumable amount->Representing random forest effects for evaluating the effect of factors on consumable consumption, < >>Representing a multiple linear regression model for predicting consumable consumption from a plurality of variables,，/>wherein->，/>，…，/>Is a regression coefficient; />，/>，…，/>Is a factor affecting consumable consumption, +.>，Is a trend adjustment factor, ++>Is the rate of change of trend; />，/>Is an exponentially smoothed value, ">Is an exponentially smoothed smoothing coefficient, +.>Is the time point->Consumable consumption of->Is a risk adjustment factor that is used to adjust the risk,，/>is a risk rate estimated based on historical data variability and predictive uncertainty,/for example>Is the consumption trend of consumables after seasonal adjustment, </i >>，/>Is based on the future consumable consumption trend of the prediction model,wherein->Is the corresponding time weighting factor,/->Is the length of time of the historical data.
Further, extracting key features from real-time data associated with the consumable and historical usage data of the consumable includes:
by passing throughExtracting key characteristics of consumable historical use data>Wherein->Is the result after the analysis of the sparse principal component,Lis the loading matrix which is to be loaded,Sis a scoring matrix->And->Is a sparsity parameter, ++>Is->Norms (F/F)>Is thatL 1 Norms (F/F)>Is the original data;
historical usage data for consumables throughPerforming analysis to obtain analysis result, wherein ∈>Is thatARMAModel (S)>Is->Individual autoregressive coefficients, < >>Is->Moving average coefficient>Is an external regression variable, ++>Is an external variable coefficient;
according to the real-time data and a preset real-time prediction model, the demand of the consumable in the future is obtained;
and fusing the features extracted from the analysis result and the demand of the future consumable to obtain a key feature comprehensive feature set.
Further, determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point, including:
by passing throughCalculating a center point, wherein each +.>Represents->Weight of dimension->Is the total number of data points, +.>Indicating that the center point is at +.>Coordinates of dimension->Representing data pointsP i In->Coordinates of the dimension;
according to the center point, passCalculating the distance from each data point to the center point;
by passing throughCalculating an angle value for each data point, wherein +.>Is a data pointP i Angle in the plane of the two dimensions j and j+1.
In a second aspect, a printer consumable management apparatus includes:
the acquisition module is used for carrying out preliminary prediction on the residual consumption and the predicted depletion time of the consumable according to a preset consumable prediction model and the real-time state of the consumable so as to obtain a first prediction result; dynamically adjusting the influence factors according to the first prediction result and the historical data to obtain dynamic influence factors;
the processing module is used for predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors so as to obtain a second prediction result; calculating a final consumable replacement time point according to the second prediction result and the historical data; and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
In a third aspect, a computing device includes:
one or more processors;
and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described methods.
In a fourth aspect, a computer readable storage medium stores a program that when executed by a processor implements the above method.
The scheme of the invention at least comprises the following beneficial effects:
through the accurate prediction to the consumption of consumptive material surplus and the consumption time of prediction, can maximize the availability factor of consumptive material, reduce extravagant. By combining the first and second prediction results and the historical data, the optimal consumable replacement time point can be accurately calculated, and the problem of replacing consumable too early or too late is avoided. By dynamically adjusting the influence factors, the prediction model can be better adapted to different printing environments and user habits, and the accuracy of prediction is improved. The automatic sending of the consumable replacement reminding information reduces the complexity that the user needs to continuously check the consumable state, and improves the user experience. Accurate consumable management can help a user or business save the cost of purchasing consumables and reduce the disruption of work due to sudden consumable depletion. Timely replacement of consumables is helpful for maintaining printing quality, and printing quality problems caused by aging or exhaustion of consumables are avoided. Through accurate control consumable use, reduce unnecessary consumable and change, help reducing environmental pollution. Through the network function, the user can monitor the consumable state remotely, and a plurality of printers are convenient to manage, so that the method is particularly suitable for large office environments.
Drawings
Fig. 1 is a flowchart of a method for managing consumables of a printer according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a consumable management device for a printer according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described more closely below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a method for managing consumables of a printer, including:
step 11, performing preliminary prediction on the residual consumption and the predicted depletion time of the consumable according to a preset consumable prediction model and the real-time state of the consumable to obtain a first prediction result;
step 12, dynamically adjusting the influence factors according to the first prediction result and the historical data to obtain dynamic influence factors;
step 13, predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors to obtain a second prediction result;
step 14, calculating a final consumable replacement time point according to the second prediction result and the historical data;
and step 15, sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
In the embodiment of the invention, the use efficiency of the consumable can be maximized and the waste can be reduced by accurately predicting the residual use amount and the predicted depletion time of the consumable. By combining the first and second prediction results and the historical data, the optimal consumable replacement time point can be accurately calculated, and the problem of replacing consumable too early or too late is avoided. By dynamically adjusting the influence factors, the prediction model can be better adapted to different printing environments and user habits, and the accuracy of prediction is improved. The automatic sending of the consumable replacement reminding information reduces the complexity that the user needs to continuously check the consumable state, and improves the user experience. Accurate consumable management can help a user or business save the cost of purchasing consumables and reduce the disruption of work due to sudden consumable depletion. Timely replacement of consumables is helpful for maintaining printing quality, and printing quality problems caused by aging or exhaustion of consumables are avoided. Through accurate control consumable use, reduce unnecessary consumable and change, help reducing environmental pollution. Through the network function, the user can monitor the consumable state remotely, and a plurality of printers are convenient to manage, so that the method is particularly suitable for large office environments.
In a preferred embodiment of the present invention, the step 11 may include:
step 111, acquiring real-time data related to the consumable and historical usage data of the consumable;
step 112, extracting key features according to real-time data related to the consumable and historical usage data of the consumable;
step 113, determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point;
step 114, mapping each data point to a corresponding position on the circumference according to the angle value corresponding to each data point;
step 115, calculating the distance between each data point and the circle center according to the corresponding position of each data point on the circle;
step 116, screening each data point according to the distance between each data point and the circle center to obtain screening data;
step 117, preprocessing the screening data to obtain preprocessed data;
and 118, predicting the residual consumption and the predicted depletion time of the consumable according to the preprocessing data and a preset consumable prediction model to obtain a first prediction result.
In the embodiment of the invention, the accuracy of prediction can be ensured by acquiring the real-time data and the historical use data related to the consumable; by mapping the data points to the circumference, the novel relevance among the data can be found, and the depth and the breadth of data analysis can be improved; the distance between the data point and the circle center is calculated, and abnormal values or irrelevant data can be removed by screening, so that the accuracy and stability of the prediction model are ensured; the screened data is preprocessed, so that the data quality can be further improved. The preprocessed high-quality data and the preset consumable prediction model are used for prediction, so that a more accurate first prediction result can be obtained, and the influence factors can be adjusted dynamically and accurately in the subsequent steps, and the final consumable replacement time point can be calculated.
In another preferred embodiment of the present invention, the step 111 may include:
step 1111, according to the usage pattern and change rate of the consumable, byDynamically adjusting the frequency of data acquisition;
step 1112, based on the real-time data, the history data, and the external data source, byData acquisition is performed, wherein->Is data acquisition requirement, < >>And->Average usage and standard deviation of historical data, respectively +.>Is a resource limitation, +.>Is the data acquisition frequency, < >>Is atTime->Is used in the amount of consumable material of the (a),U opt is the result of data collection,/->Is a historical usage data set,/->Is constant, & lt>Is a weight coefficient.
In a preferred embodiment of the present invention, the step 12 may include:
step 121, obtaining a first prediction resultData set +.>Wherein, the method comprises the steps of, wherein,，/>is a consumable predictive model parameter set,/->Representing historical dataset +.>The%>Individual observations->And->Corresponding consumable predictive model parameters;
step 122, byCalculating dynamic influence factor->Wherein->={/>，/>，…，/>… is the parameter set of the influence factor adjustment model, +.>And->Is the influence factor to adjust the model parameters,/->Is thatsigmoidAnd a function for smoothing and adjusting the influence of the prediction result and the history data.
In the embodiment of the invention, necessary basic data is provided for dynamic adjustment by acquiring the first prediction result and the related data set, and the consumable prediction model parameter set and the historical data observation value, so that the accuracy and the relevance of the adjustment of the influence factors are ensured. The prediction strategy can be adjusted according to the current prediction result and the actual performance of the historical data by adjusting the model through the dynamic influence factors, and the adaptability and the accuracy of the prediction model are improved. The dynamic adjustment influence factor means that the prediction model can be self-adjusted according to new data and conditions, and the self-adaptive capacity enables prediction to be more accurate, and meanwhile the number of times of manual intervention is reduced. By comprehensively considering historical data and current prediction and adjusting influence factors through nonlinear functions, the robustness of the whole prediction system is improved, and fluctuation and uncertainty of data can be better processed.
In a preferred embodiment of the present invention, the step 13 may include:
step 131, set upARMA(p，q) The order of the autoregressive terms is represented aspThe order of the moving average term isqThe time series model of consumable consumption data is:wherein->Andis a time series model parameter, < >>Is an error term->Is a trend component->Is a seasonal component;
step 132, byPredicting the remaining consumption of the consumable and the predicted depletion time to obtain a second prediction result +.>Wherein->Is historical consumption data, < >>Is a dynamic influencing factor, ++>Is a machine learning model for predicting the remaining amount of consumable,wherein->，/>，And->Parameters (I)>Is a function for calculating the expected depletion time.
In the embodiment of the invention, byARMA(p，q) The model is used for analyzing the time sequence of consumable consumption data, and can capture the autoregressive characteristics and the moving average characteristics in the data, so that the time sequence analysis is more comprehensive and deeper; step 132 not only uses historical consumption data and dynamic influence factors, but also introduces a machine learning model, so that the consumable remaining amount and the consumption time can be more comprehensively analyzed and predicted, and the prediction accuracy and reliability are improved. The second prediction result is obtained based on multiple dimensions and technologies, not only comprises a time series analysis result, but also combines the prediction of a machine learning model, and the comprehensive analysis and prediction helps to obtain a more comprehensive and accurate prediction result.
In a preferred embodiment of the present invention, the step 14 may include:
step 141, may be performed byCalculate the final replacement consumable time point +.>，/>Indicates the current time, ++>Indicating the remaining consumable amount->Representing random forest effects for evaluating the effect of factors on consumable consumption, < >>Representing a multiple linear regression model for predicting consumable consumption from a plurality of variables +.>，Wherein->，/>，…，/>Is a regression coefficient; />，/>，…，/>Is a factor affecting consumable consumption, +.>，/>Is a trend adjustment factor, ++>Is the rate of change of trend;，/>is an exponentially smoothed value, ">Is an exponentially smoothed smoothing coefficient, +.>Is the point in timeConsumable consumption of->Is a risk adjustment factor,/->，/>Is a risk rate estimated based on historical data variability and predictive uncertainty, SA is a seasonal adjusted consumable consumption trend, +.>FC is the future consumable consumption trend based on predictive model, < >>Wherein->Is the corresponding time weighting factor and n is the time length of the historical data.
In the embodiment of the invention, the optimal consumable replacement time is determined by calculating the final consumable replacement time point, so that the final time point judgment is comprehensive and accurate. By using a random forest model and a multiple linear regression model, the machine learning is combined with the traditional statistical method, and the accuracy of predicting consumable consumption is improved. The random forest model is used for evaluating the influence of each factor on consumable consumption, and the multiple linear regression model predicts consumable consumption from a plurality of variables, so that the predicted comprehensiveness and multidimensional degree are ensured. Through the risk adjustment factors and consumption trends of the consumables after seasonal adjustment, risks brought by data variability and prediction uncertainty are considered, influence of the seasonal factors on consumption of the consumables is considered, complexity of a prediction model is increased, and practicality and accuracy are greatly improved. By using the techniques of exponential smoothing values, trend adjustment factors and the like, the abnormal fluctuation in the historical data can be smoothed, the consumable consumption trend in the future can be accurately predicted, more robust decision support is provided, and more reliable consumable management decisions can be made. Accurately predicting consumable replacement time points can help to manage inventory more effectively, avoid over-purchase or consumable shortage, and thereby reduce costs and resource waste.
In a preferred embodiment of the present invention, the step 112 may include:
step 1121, byExtracting key characteristics of consumable historical use data>Wherein->Is the result after the analysis of the sparse principal component,Lis the loading matrix which is to be loaded,Sis a scoring matrix->And->Is a sparsity parameter, ++>Is->Norms (F/F)>Is thatL 1 Norms (F/F)>Is the original data;
step 1122, historical usage data for consumable by
Performing analysis to obtain analysis result, wherein ∈>Is thatARMAModel (S)>Is->Individual autoregressive coefficients, < >>Is->Moving average coefficient>Is an external regression variable, ++>Is an external variable coefficient;
step 1123, obtaining the demand of the consumable in the future according to the real-time data and the preset real-time prediction model;
step 1124, fusing the features extracted from the analysis results and the demand of future consumables to obtain a key feature comprehensive feature set.
In an embodiment of the present invention, step 1121 effectively extracts key features from consumable historical usage data by applying sparse principal component analysis. Sparse principal component analysis not only reduces the dimensionality of the data, but also retains the most important information, which makes subsequent analysis and prediction more accurate and efficient. The application of sparsity parameters further enhances the interpretability of the model, making key features easier to understand and apply. Step 1122 may provide an in-depth understanding of the time-series nature of consumable consumption. This approach not only considers autoregressive and moving average factors, but also includes the influence of external regression variables, thereby providing a comprehensive and thorough analysis of consumable usage. Step 1123 is capable of predicting the demand of future consumables, and real-time prediction is crucial to rapidly respond to market changes and adjust inventory strategies, which helps to ensure timeliness and efficiency of consumable supply. Step 1124 creates a comprehensive feature set. The fusion not only improves the comprehensiveness of data analysis, but also enhances the accuracy and reliability of the prediction model. The comprehensive feature set can provide a more comprehensive view to the decision maker, helping them make more intelligent decisions.
In a preferred embodiment of the present invention, the step 113 may include:
step 1131, byCalculating a center point, wherein each +.>Represents->Weight of dimension->Is the total number of data points, +.>Indicating that the center point is at +.>Coordinates of dimension->Representing data pointsP i In->Coordinates of the dimension;
step 1132, based on the center point, byCalculating the distance from each data point to the center point;
by passing throughCalculating an angle value for each data point, wherein +.>Is a data pointP i Angle in the plane of the two dimensions j and j+1.
In an embodiment of the present invention, step 1131 determines the center position of the data in the multidimensional space. In this process, the weight of each dimension is taken into account, and such weight allocation can help to better understand the importance of different features in the overall structure of the data. Step 1132, by calculating the distance from each data point to the center point, can quantify the deviation degree of the data points and the whole center of the data set, and is very useful for identifying abnormal values, understanding the distribution characteristics of the data and carrying out group division; by calculating the angle of the data points in the two dimensional planes, the angle information may reveal the relative positional relationship between the data points, which may be more insight in some cases than mere distance information. For example, angular analysis may help maintain the relative relationship between data points when performing a dimension-reduction analysis of high-dimensional data.
In another preferred embodiment of the present invention, the step 114 may include:
step 1141, according to the angle value corresponding to each data point, passingMapping each data point to a corresponding position on the circumference, respectively, < >>Wherein R is the radius of the sphere, +.>Is a data pointP i In the first placejSum of the first and secondjAngle on plane between +1 dimensions, +.>Is a normalization factor that is used to normalize the data,kis an index of the number of the words,nrepresenting data pointsP i Total number of dimensions in high-dimensional space.
In another preferred embodiment of the present invention, the step 115 may include:
step 1151, for each data pointP i At the position ofnCoordinates in dimensional spaceBy means ofCalculate each data pointP i With reference pointCDistance betweenD i Wherein->Is a data pointP i In the first placekCoordinates of dimension->Is the reference pointCIn the first placekCoordinates of dimension->Is the firstkWeight coefficient of dimension,/->Is a regulatory factor, wherein->，/>，/>Is not considered->Maximum value of all distances calculated at that time, < +.>Representing +.>Dimension(s) (i.e.)>Is->Number of data points.
In another preferred embodiment of the present invention, the step 116 may include:
step 1161, byCalculating a dynamic distance threshold +.>，
Step 1162, byComputing data point dynamic weight threshold +.>；
Step 1162, screening out the distance less than or equal toAnd the weight is not less than%>Of (1), wherein->Is the average distance of all data points to the center, +.>Is the standard deviation of the distance>Is a regulator, and is a->Is the +.o. of the distance from the data point to the center of the circle>The number of the sub-digits is calculated,is a trade-off coefficient->Weight set representing all data points, +.>Is the variance of the weights, +.>Is the bias of the weight, +.>And，/>is a regulatory factor.
As shown in fig. 2, an embodiment of the present invention further provides a printer consumable management device 20, including:
the obtaining module 21 is configured to preliminarily predict a remaining usage amount and a predicted depletion time of the consumable according to a preset consumable prediction model and a real-time status of the consumable, so as to obtain a first prediction result; dynamically adjusting the influence factors according to the first prediction result and the historical data to obtain dynamic influence factors;
the processing module 22 is configured to predict a remaining usage amount of the consumable and a predicted depletion time according to the dynamic impact factor, so as to obtain a second prediction result; calculating a final consumable replacement time point according to the second prediction result and the historical data; and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
Optionally, according to a preset consumable prediction model and a real-time state of the consumable, performing preliminary prediction on a remaining usage amount and a predicted depletion time of the consumable to obtain a first prediction result, where the method includes:
acquiring real-time data related to the consumable and historical use data of the consumable;
extracting key features according to real-time data related to the consumable and historical use data of the consumable;
determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point;
mapping each data point to a corresponding position on the circumference according to the angle value corresponding to each data point;
calculating the distance between each data point and the circle center according to the corresponding position of each data point on the circle;
screening each data point according to the distance between each data point and the circle center to obtain screening data;
preprocessing the screening data to obtain preprocessed data;
and predicting the residual consumption and the predicted depletion time of the consumable according to the preprocessing data and a preset consumable prediction model to obtain a first prediction result.
Optionally, dynamically adjusting the influence factor according to the first prediction result and the historical data to obtain a dynamic influence factor, including:
acquiring a first prediction resultData set +.>Wherein, the method comprises the steps of, wherein,，/>is a consumable predictive model parameter set,/->Representing historical dataset +.>The%>Individual observations->And->Corresponding consumable predictive model parameters;
by passing throughCalculating dynamic influence factor->Wherein->={/>，/>，…，/>… is the parameter set of the influence factor adjustment model, +.>And->Is the influence factor to adjust the model parameters,/->Is thatsigmoidAnd a function for smoothing and adjusting the influence of the prediction result and the history data.
Optionally, predicting the remaining consumption of the consumable and the predicted depletion time according to the dynamic influence factor to obtain a second prediction result, including:
is provided withARMA(p，q) The order of the autoregressive terms is represented aspThe order of the moving average term isqThe time series model of consumable consumption data is:wherein->And->Is a time series model parameter, < >>Is an error term->Is a trend component->Is a seasonal component;
by passing throughPredicting the residual consumption of the consumable and the predicted depletion time to obtain a second predicted junctionFruit (herba Cichorii)>Wherein->Is historical consumption data, < >>Is a dynamic influencing factor, ++>Is a machine learning model for predicting the remaining amount of consumable,wherein->，/>，And->Parameters (I)>Is a function for calculating the expected depletion time.
Optionally, calculating a final consumable replacement time point according to the second prediction result and the historical data includes:
by passing throughCalculate the final replacement consumable time point +.>DQ denotes the current time, sy denotes the amount of consumable remaining, RFI denotes the random forest influence for evaluating the influence of each factor on consumable consumption, MLR denotes a multiple linear regression model for predicting from a plurality of variablesThe consumption of the consumable material is realized, the consumable material is in a state of being,，/>wherein->，/>，…，/>Is a regression coefficient; />，/>，…，/>Is a factor affecting consumable consumption, +.>，Is a trend adjustment factor, ++>Is the rate of change of trend; />，/>Is an exponentially smoothed value, ">Is an exponentially smoothed smoothing coefficient, +.>Is the time point->Is a risk adjustment factor,r is the risk rate estimated based on historical data variability and predictive uncertainty, SA is the seasonal adjusted consumable consumption trend, +.>FC is a future consumable consumption trend based on a predictive model,wherein->Is the corresponding time weighting factor and n is the time length of the historical data.
Optionally, extracting the key feature according to real-time data related to the consumable and historical usage data of the consumable includes:
by passing throughExtracting key characteristics of consumable historical use data>Wherein->Is the result after the analysis of the sparse principal component,Lis the loading matrix which is to be loaded,Sis a scoring matrix->And->Is a sparsity parameter, ++>Is->Norms (F/F)>Is thatL 1 Norms (F/F)>Is the original data;
historical usage data for consumables throughPerforming analysis to obtain analysis result, wherein ∈>Is thatARMAModel (S)>Is->Individual autoregressive coefficients, < >>Is->Moving average coefficient>Is an external regression variable, ++>Is an external variable coefficient;
according to the real-time data and a preset real-time prediction model, the demand of the consumable in the future is obtained;
and fusing the features extracted from the analysis result and the demand of the future consumable to obtain a key feature comprehensive feature set.
Optionally, determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point, including:
by passing throughCalculating a center point, wherein each +.>Represents->Weight of dimension, m is total number of data points, +.>Indicating that the center point is at +.>Coordinates of dimension->Representing data pointsP i In->Coordinates of the dimension;
according to the center point, passCalculating the distance from each data point to the center point;
by passing throughCalculating an angle value for each data point, wherein +.>Is a data pointP i Angle in the plane of the two dimensions j and j+1.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (8)
1. A method of managing consumables of a printer, the method comprising:
according to a preset consumable prediction model and a real-time state of consumable, primarily predicting the residual consumption and predicted depletion time of the consumable to obtain a first prediction result, wherein the method comprises the following steps: acquiring real-time data related to the consumable and historical use data of the consumable; extracting key features according to real-time data related to the consumable and historical use data of the consumable; determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point; mapping each data point to a corresponding position on the circumference according to the angle value corresponding to each data point; calculating the distance between each data point and the circle center according to the corresponding position of each data point on the circle; screening each data point according to the distance between each data point and the circle center to obtain screening data; preprocessing the screening data to obtain preprocessed data; predicting the residual consumption and the predicted depletion time of the consumable according to the preprocessing data and a preset consumable prediction model to obtain a first prediction result;
dynamically adjusting the influence factor according to the first prediction result and the historical data to obtain a dynamic influence factor, wherein the method comprises the following steps: acquiring a first prediction resultAnd a data set D, wherein,，/>is a consumable predictive model parameter set,/->Represents the i-th observation in the history data set D,/->、/>And->Corresponding consumable predictive model parameters; by->Calculating dynamic influence factor->Wherein->={/>，/>，…，/>… is the parameter set of the influence factor adjustment model, +.>And->Is the influence factor to adjust the model parameters,/->Is thatsigmoidA function for smoothing and adjusting the influence of the prediction result and the history data;
predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors to obtain a second prediction result;
calculating a final consumable replacement time point according to the second prediction result and the historical data;
and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
2. The method according to claim 1, wherein predicting the remaining consumption of the consumable and the predicted depletion time according to the dynamic influence factor to obtain the second prediction result comprises:
is provided withARMA(p，q) The order of the autoregressive terms is represented aspThe order of the moving average term isqThe time series model of consumable consumption data is:wherein->And->Is a time series model parameter, < >>Is an error term->Is a trend component->Is seasonal component, ++>Expressed in timetBeforejError terms of time units;
by passing throughPredicting the remaining consumption of the consumable and the predicted depletion time to obtain a second prediction result +.>Wherein->Is historical consumption data, < >>Is a dynamic influencing factor which is used to influence the dynamic state of the device,is a machine learning model for predicting the remaining amount of consumable,wherein->，/>，，/>And->Is a parameter->Is a function for calculating the expected depletion time.
3. The method of claim 2, wherein calculating a final replacement consumable part time point based on the second prediction result and the history data, comprises:
by passing throughCalculate the final replacement consumable time point +.>，/>Indicates the current time, ++>Indicating the remaining consumable amount->Representing random forestsInfluence, for evaluating influence of each factor on consumption of consumable material,/->Representing a multiple linear regression model for predicting consumable consumption from a plurality of variables,，/>wherein->，/>，…，/>Is a regression coefficient; />，/>，…，/>Is a factor affecting consumable consumption, +.>，Is a trend adjustment factor, ++>Is the rate of change of trend; />，/>Is an exponentially smoothed value, ">Is an exponentially smoothed smoothing coefficient, +.>Is the time point->Consumable consumption of->Is a risk adjustment factor that is used to adjust the risk,，/>is a risk rate estimated based on historical data variability and predictive uncertainty,/for example>Is the consumption trend of consumables after seasonal adjustment, </i >>，/>Is based on the future consumable consumption trend of the prediction model,wherein->Is the corresponding time weighting factor,/->Is the length of time of the historical data.
4. A method of managing printer consumables according to claim 3, wherein extracting key features based on real-time data associated with the consumables and historical usage data of the consumables comprises:
by passing throughExtracting key characteristics of consumable historical use data>Wherein->Is the result after the analysis of the sparse principal component,Lis the loading matrix which is to be loaded,Sis a scoring matrix->And->Is a sparsity parameter, ++>Is->Norms (F/F)>Is thatL 1 Norms (F/F)>Is the original data;
historical usage data for consumables throughPerforming analysis to obtain analysis resultsWherein->Is thatARMAModel (S)>Is->Individual autoregressive coefficients, < >>Is->Moving average coefficient>Is an external regression variable, ++>Is an external variable coefficient, +.>Expressed in timetBeforepConsumable usage data of time units, +.>Expressed in timetBeforeqError terms of time units;
according to the real-time data and a preset real-time prediction model, the demand of the consumable in the future is obtained;
and fusing the features extracted from the analysis result and the demand of the future consumable to obtain a key feature comprehensive feature set.
5. The method of claim 4, wherein determining the center and the radius, and calculating the respective angle value for each data point based on the respective characteristic value for each data point, comprises:
by passing throughCalculating a center point, wherein each +.>Represents->Weight of dimension->Is the total number of data points, +.>Indicating that the center point is at +.>Coordinates of dimension->Representing data pointsP i In->Coordinates of the dimension;
according to the center point, passCalculating the distance from each data point to the center point;
by passing throughCalculating an angle value for each data point, wherein +.>Is a data pointP i In two dimensionsjAndjangle in +1 plane.
6. A printer consumable management apparatus, comprising:
the acquisition module is used for carrying out preliminary prediction on the residual consumption of the consumable and the predicted depletion time according to a preset consumable prediction model and the real-time state of the consumable so as to obtain a first prediction result, and comprises the following steps: acquiring real-time data related to the consumable and historical use data of the consumable; extracting key features according to real-time data related to the consumable and historical use data of the consumable; determining the circle center and the radius, and calculating the angle value corresponding to each data point according to the characteristic value corresponding to each data point; mapping each data point to a corresponding position on the circumference according to the angle value corresponding to each data point; calculating the distance between each data point and the circle center according to the corresponding position of each data point on the circle; screening each data point according to the distance between each data point and the circle center to obtain screening data; preprocessing the screening data to obtain preprocessed data; predicting the residual consumption and the predicted depletion time of the consumable according to the preprocessing data and a preset consumable prediction model to obtain a first prediction result; dynamically adjusting the influence factor according to the first prediction result and the historical data to obtain a dynamic influence factor, wherein the method comprises the following steps: acquiring a first prediction resultAnd a data set D, wherein,，/>is a consumable predictive model parameter set,/->Representing historical dataset +.>The%>Individual observations->、/>And->Corresponding consumable predictive model parameters; by->Calculating dynamic influence factor->Wherein->={/>，/>，…，/>… is the parameter set of the influence factor adjustment model, +.>And->Is the influence factor to adjust the model parameters,/->Is thatsigmoidFunction for smoothing and adjusting predicted junctionsEffects of fruit and historical data;
the processing module is used for predicting the residual consumption of the consumable and the predicted depletion time according to the dynamic influence factors so as to obtain a second prediction result; calculating a final consumable replacement time point according to the second prediction result and the historical data; and sending reminding information to a preset user side through a network according to the second prediction result and the final consumable replacement time point.
7. A computing device, comprising:
one or more processors;
storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1 to 5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410141771.6A CN117707442B (en) | 2024-02-01 | 2024-02-01 | Printer consumable management method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410141771.6A CN117707442B (en) | 2024-02-01 | 2024-02-01 | Printer consumable management method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117707442A CN117707442A (en) | 2024-03-15 |
| CN117707442B true CN117707442B (en) | 2024-04-16 |
Family
ID=90146437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410141771.6A Active CN117707442B (en) | 2024-02-01 | 2024-02-01 | Printer consumable management method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117707442B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019075020A (en) * | 2017-10-18 | 2019-05-16 | シヤチハタ株式会社 | Consumable material managing system and consumable material managing method |
| WO2023050275A1 (en) * | 2021-09-30 | 2023-04-06 | 京东方科技集团股份有限公司 | Data processing method and system, and computer readable storage medium |
| CN117032601A (en) * | 2023-10-09 | 2023-11-10 | 深圳鼎力数码科技有限公司 | Real-time monitoring method and system for printing consumables |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9046854B2 (en) * | 2013-06-27 | 2015-06-02 | Xerox Corporation | Estimating accuracy of a remaining useful life prediction model for a consumable using statistics based segmentation technique |
| US11809930B2 (en) * | 2020-12-28 | 2023-11-07 | MPS Monitor srl | System and method for accurately managing the consumables of a printer fleet |
-
2024
- 2024-02-01 CN CN202410141771.6A patent/CN117707442B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019075020A (en) * | 2017-10-18 | 2019-05-16 | シヤチハタ株式会社 | Consumable material managing system and consumable material managing method |
| WO2023050275A1 (en) * | 2021-09-30 | 2023-04-06 | 京东方科技集团股份有限公司 | Data processing method and system, and computer readable storage medium |
| CN117032601A (en) * | 2023-10-09 | 2023-11-10 | 深圳鼎力数码科技有限公司 | Real-time monitoring method and system for printing consumables |
Non-Patent Citations (1)
| Title |
|---|
| 基于自回归积分滑动平均模型的医用低值耗材需求量预测研究;许亮业;张琪;张诚;;中国医疗设备;20170725(第07期);第159-161页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117707442A (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663493B2 (en) | Method and system of dynamic model selection for time series forecasting | |
| CN111724278A (en) | Fine classification method and system for power multi-load users | |
| CN105786711A (en) | Data analysis method and device | |
| Liu et al. | Feature selection for software effort estimation with localized neighborhood mutual information | |
| CN112488507A (en) | Expert classification portrait method and device based on clustering and storage medium | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN112614011A (en) | Power distribution network material demand prediction method and device, storage medium and electronic equipment | |
| CN112884570A (en) | Method, device and equipment for determining model security | |
| CN117707442B (en) | Printer consumable management method and device | |
| CN114155072A (en) | Financial prediction model construction method and system based on big data analysis | |
| CN116909712A (en) | Intelligent task scheduling system and method based on machine learning | |
| CN116774986A (en) | Automatic evaluation method and device for software development workload, storage medium and processor | |
| CN114077977B (en) | Building intelligent management method and system based on big data and readable storage medium | |
| CN109978038B (en) | Cluster abnormity judgment method and device | |
| CN117471873B (en) | Printer carbon powder supply control method and device | |
| CN116957306B (en) | User side response potential evaluation method and system based on resource collaborative interaction | |
| Bystrov et al. | Choosing the Number of Topics in LDA Models--A Monte Carlo Comparison of Selection Criteria | |
| CN116451874B (en) | Urban water consumption prediction method, device and equipment | |
| CN117609923B (en) | Electronic information processing system and method for Internet of things | |
| CN117764620A (en) | User loss early warning method and device | |
| CN112329351A (en) | Flow analysis system and method based on data tracking | |
| CN117149107A (en) | Method for reducing emission in printing of cultural products | |
| Fentanes et al. | Growth and the firm-size distribution over the long-run | |
| Kiefer | The Valuation of Economic Information | |
| Sekar et al. | Micro, Small and Medium Enterprises Control Financial Cost Accounting based on Artificial Intelligence and Data Mining Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |